Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    a variety of sentence fragments, seemingly at random

    oai_token-act-pair · gemini-2.0-flash

    code/technical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.50
    0
    -0.50
    2
    -0.49
     удовольствием
    -0.48
    ori
    -0.46
    va
    -0.45
    ck
    -0.45
    .
    -0.44
     pensare
    -0.43
    6
    -0.43
    POSITIVE LOGITS
     GenerationType
    0.96
    complexContent
    0.89
     AssemblyProduct
    0.87
    Referanser
    0.84
     ***!
    0.82
    تقاوى
    0.75
     contextLoads
    0.75
     esternos
    0.75
    Билгалдахарш
    0.74
    IVEREF
    0.73
    Act Density 1.799%

    No Known Activations